Jinmei Lai

Jinmei Lai


Research Focus & Metrics

Academic Career Length

22Years (2005-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 August 2021 in IEICE Transactions on Information and Systems
Verified
Journal Article
Closed access
PDF file
JGJiabao Gao
Jiabao Gao
YYYuchen Yao
Yuchen Yao
ZLZhengjie Li
Zhengjie Li
JLJinmei Lai
Jinmei Lai
A series of Binarized Neural Networks (BNNs) show the accepted accuracy in image classification tasks and achieve the excellent performance on field programmable gate array (FPGA). Nevertheless, we observe existing designs of BNNs are quite time-consuming in change of the target BNN and acceleration of a new BNN. Therefore, this paper presents FCA-BNN, a flexible and configurable accelerator, which employs the layer-level configurable technique to execute seamlessly each layer of target BNN. Initially, to save resource and improve energy efficiency, the hardware-oriented optimal formulas are introduced to design energy-efficient computing array for different sizes of padded-convolution and fully-connected layers. Moreover, to accelerate the target BNNs efficiently, we exploit the analytical model to explore the optimal design parameters for FCA-BNN. Finally, our proposed mapping flow changes the target network by entering order, and accelerates a new network by compiling and loading corresponding instructions, while without loading and generating bitstream. The evaluations on three major structures of BNNs show the differences between inference accuracy of FCA-BNN and that of GPU are just 0.07%, 0.31% and 0.4% for LFC, VGG-like and Cifar-10 AlexNet. Furthermore, our energy-efficiency results achieve the results of existing customized FPGA accelerators by 0.8× for LFC and 2.6× for VGG-like. For Cifar-10 AlexNet, FCA-BNN achieves 188.2× and 60.6× better than CPU and GPU in energy efficiency, respectively. To the best of our knowledge, FCA-BNN is the most efficient design for change of the target BNN and acceleration of a new BNN, while keeps the competitive performance.

12 October 2021 in IEEE Transactions on Circuits and Systems II: Express Briefs
Verified
Journal Article
Closed access
QLQingliang Liu
Qingliang Liu
JLJinmei Lai
Jinmei Lai
JGJiabao Gao
Jiabao Gao
The binarized neural network (BNN) inference accelerators show great promise in cost- and power-restricted domains. However, the performances of these accelerators are still severely limited by the significant redundancies in BNNs inference. In this brief, we introduce channel-aware sparse accelerator (CAA) to alleviate the performance degradations induced by the redundancies in BNNs while maintaining original accuracies. First, motivated by the observation that the convolution processes of our rebuilt rectangle kernels contain many redundant operations which can be skipped by exploiting the BNN-specific property, we convert the entire original XNOR-popcount convolutions of each neuron into channel-aware-popcount (CAP) operations for all binarized convolutional and fully-connected layers in CAA by employing rectangle kernel simplification strategy and eliminate the unnecessary operations. Meanwhile, these CAP operations can be implemented to directly gain the final output without any extra steps. Furthermore, inspired by our new observations on two specific kinds of properties of the CAP operations, we adopt group pruning approach to save the remaining redundant CAP operations. Experimental results show that our design evaluated on an embedded FPGA achieves 4.2- $6.6{\times }$ inference-speedup, 3.6- $5.5{\times }$ energy-efficiency enhancement, and $1.35{\times }$ resource-efficiency improvement compared with state-of-the-art works.

1 January 2018 in IEICE Electronics Express
Verified
Journal Article
Closed access
PDF file
HXHanyang Xu
Hanyang Xu
JWJian Wang
Jian Wang
JLJinmei Lai
Jinmei Lai
A self-adaptive technique is presented for a low voltage differential signaling (LVDS) driver. By combining a high speed voltage detection circuit and drive capability control loop, the proposed architecture can adapt to the changes of output load and operating frequency automatically. This makes the driver suitable for using in field programmable gate array (FPGA), where load and frequency variation is large. Compared to previously reported LVDS drivers with fixed drive capability, the proposed driver eliminates power wasting under small load and low frequency condition. A prototype chip has been fabricated in 130 nm CMOS technology. Test results show the proposed driver improves maximum bit rate to 2.2 Gb/s and reduces power consumption by 48% compared to previously reported works with fixed drive capability.

30 July 2021 in Electronics
Verified
Journal Article
Open access
PDF file
JGJiabao Gao
Jiabao Gao
FHfu hao
fu hao
JLJinmei Lai
Jinmei Lai
Binarized neural networks (BNNs), which have 1-bit weights and activations, are well suited for FPGA accelerators as their dominant computations are bitwise arithmetic, and the reduction in memory requirements means that all the network parameters can be stored in internal memory. However, the energy efficiency of these accelerators is still restricted by the abundant redundancies in BNNs. This hinders their deployment for applications in smart sensors and tiny devices because these scenarios have tight constraints with respect to energy consumption. To overcome this problem, we propose an approach to implement BNN inference while offering excellent energy efficiency for the accelerators by means of pruning the massive redundant operations while maintaining the original accuracy of the networks. Firstly, inspired by the observation that the convolution processes of two related kernels contain many repeated computations, we first build one formula to clarify the reusing relationships between their convolutional outputs and remove the unnecessary operations. Furthermore, by generalizing this reusing relationship to one tile of kernels in one neuron, we adopt an inclusion pruning strategy to further skip the superfluous evaluations of the neurons whose real output values can be determined early. Finally, we evaluate our system on the Zynq 7000 XC7Z100 FPGA platform. Our design can prune 51 percent of the operations without any accuracy loss. Meanwhile, the energy efficiency of our system is as high as 6.55 × 105 Img/kJ, which is 118× better than the best accelerator based on an NVDIA Tesla-V100 GPU and 3.6× higher than the state-of-the-art FPGA implementations for BNNs.

28 February 2024 in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Verified
Journal Article
Closed access
WXWei Xiong
Wei Xiong
JCJiacheng Cao
Jiacheng Cao
YLYaozhang Liu
Yaozhang Liu
JWJian Wang
Jian Wang
JLJinmei Lai
Jinmei Lai
MHMiaoqing Huang
Miaoqing Huang
Adaptive voltage and frequency scaling (AVFS) technology adjusts the supply voltage and clock frequency based on the actual operating conditions of the circuit. It can significantly improve performance or reduce the power consumption of the device. Existing online field-programmable gate array (FPGA) AVFS solutions have relatively low adjustment efficiency. Many existing solutions rely on offline steps, which do not consider the runtime operating conditions. This article proposes a complete FPGA AVFS solution, which includes a versatile self-checking timing monitor (SCTM) with small resource overhead, efficient AVFS algorithms without any offline steps, and user-friendly comprehensive automation software. Compared with existing online solutions, the proposed solution improves scaling efficiency by reducing the number of configuration times for the clock generation unit. The effectiveness of the solution is evaluated by a set of pubic benchmarks. Experimental results indicate that it can set an appropriate voltage–frequency operating point for the application circuit within dozens of milliseconds. For power-oriented adjustment, the proposed solution can save power ranging from 33.93% to 43.46%, while keeping the frequency not slower than the one reported by the static timing analysis (STA). For performance-oriented adjustment, it can achieve a performance improvement ranging from 60.26% to 101.90% at the nominal voltage.

1 September 2011 in Journal of Semiconductors
Verified
Journal Article
Closed access
PDF file
XDXueyan Duan
Xueyan Duan
LWLiyun Wang
Liyun Wang
JLJinmei Lai
Jinmei Lai
This paper presents three new types of pulse quenching mechanism (NMOS-to-PMOS, PMOS-to-NMOS and NMOS-to-NMOS) and verifies them using 3-D TCAD mixed mode simulations at the 90 nm node. The three major contributions of this paper are: (1) with the exception of PMOS-to-PMOS, pulse quenching is also prominent for PMOS-to-NMOS and NMOS-to-NMOS in a 90 nm process. (2) Pulse quenching in general correlates weakly with ion LET, but strongly with incident angle and layout style (i.e. spacing between transistors and n-well contact area). (3) Compact layout and cascaded inverting stages can be utilized to promote SET pulse quenching in combinatorial circuits.